Underwater video analysis

BisQue has been used to manage and analyze 23.3 hours (884GB) of high definition video from dives in Bering Sea submarine canyons to evaluate the density of fishes, structure-forming corals and sponges and to document and describe fishing damage. Non-overlapping frames were extracted from each video transect at a constant frequency of 1 frame per 30s. An image processing algorithm developed in Matlab was used to detect laser dots projected onto the seafloor as a scale reference. BisQue's module system allows to wrap this Matlab code into an analysis module that can be parallelized across a compute cluster. In addition, each frame was manually annotated with objects of interest (e.g., fishes, sponges, substrates) and these annotations and other image metadata (e.g., pixel resolution, GPS location) was stored in BisQue's flexible metadata store. The annotations were then used to compute the average density of species and co-habitation behavior in different regions of the canyons, resulting in new insights into this ecosystem.